app.py

import gradio as gr
from dotenv import load_dotenv
from roboflow import Roboflow
import tempfile
import os
import requests
import cv2
import numpy as np

# ========== Konfigurasi ========== 
load_dotenv()

# Roboflow Config
rf_api_key = os.getenv("ROBOFLOW_API_KEY")
workspace = os.getenv("ROBOFLOW_WORKSPACE")
project_name = os.getenv("ROBOFLOW_PROJECT")
model_version = int(os.getenv("ROBOFLOW_MODEL_VERSION"))

# OWLv2 API Config
OWLV2_API_URL = "https://api.landing.ai/v1/tools/text-to-object-detection"
OWLV2_PROMPTS = ["beverage", "bottle", "cans", "boxed milk", "milk"]

# Inisialisasi Model YOLO
rf = Roboflow(api_key=rf_api_key)
project = rf.workspace(workspace).project(project_name)
yolo_model = project.version(model_version).model

# ========== Fungsi Deteksi Kombinasi ========== 
def detect_combined(image):
    with tempfile.NamedTemporaryFile(delete=False, suffix=".jpg") as temp_file:
        image.save(temp_file, format="JPEG")
        temp_path = temp_file.name

    try:
        # ========== [1] YOLO: Deteksi Produk Nestlé (Per Class) ========== 
        yolo_pred = yolo_model.predict(temp_path, confidence=50, overlap=80).json()
        
        nestle_class_count = {}
        nestle_boxes = []
        for pred in yolo_pred['predictions']:
            class_name = pred['class']
            nestle_class_count[class_name] = nestle_class_count.get(class_name, 0) + 1
            nestle_boxes.append((pred['x'], pred['y'], pred['width'], pred['height']))
        
        total_nestle = sum(nestle_class_count.values())

        # ========== [2] OWLv2: Deteksi Kompetitor ========== 
        with open(temp_path, "rb") as image_file:
            response = requests.post(OWLV2_API_URL, 
                                     files={"image": image_file},
                                     data={"prompts": OWLV2_PROMPTS, "model": "owlv2"})
        
        owlv2_pred = response.json().get("objects", [])
        
        competitor_class_count = {}
        competitor_boxes = []
        for obj in owlv2_pred:
            x1, y1, x2, y2 = obj["bbox"]
            class_name = obj["label"].strip().lower()
            if not is_overlap((x1, y1, x2, y2), nestle_boxes):
                competitor_class_count[class_name] = competitor_class_count.get(class_name, 0) + 1
                competitor_boxes.append({"class": class_name, "box": (x1, y1, x2, y2), "confidence": obj["score"]})
        
        total_competitor = sum(competitor_class_count.values())
        
        # ========== [3] Format Output ========== 
        result_text = "Product Nestle\n\n"
        for class_name, count in nestle_class_count.items():
            result_text += f"{class_name}: {count}\n"
        result_text += f"\nTotal Products Nestle: {total_nestle}\n\n"
        result_text += f"Total Unclassified Products: {total_competitor}\n" if competitor_class_count else "No Unclassified Products detected\n"

        # ========== [4] Visualisasi ========== 
        img = cv2.imread(temp_path)
        
        for pred in yolo_pred['predictions']:
            x, y, w, h = pred['x'], pred['y'], pred['width'], pred['height']
            cv2.rectangle(img, (int(x-w/2), int(y-h/2)), (int(x+w/2), int(y+h/2)), (0,255,0), 2)
            cv2.putText(img, pred['class'], (int(x-w/2), int(y-h/2-10)), cv2.FONT_HERSHEY_SIMPLEX, 0.55, (0,255,0), 2)
        
        for comp in competitor_boxes:
            x1, y1, x2, y2 = comp['box']
            display_name = "unclassified" if comp['class'] in OWLV2_PROMPTS else comp['class']
            cv2.rectangle(img, (int(x1), int(y1)), (int(x2), int(y2)), (0, 0, 255), 2)
            cv2.putText(img, f"{display_name} {comp['confidence']:.2f}", (int(x1), int(y1-10)), cv2.FONT_HERSHEY_SIMPLEX, 0.55, (0, 0, 255), 2)
            
        output_path = "/tmp/combined_output.jpg"
        cv2.imwrite(output_path, img)

        return output_path, result_text

    except Exception as e:
        return temp_path, f"Error: {str(e)}"
    finally:
        os.remove(temp_path)


def is_overlap(box1, boxes2, threshold=0.3):
    x1_min, y1_min, x1_max, y1_max = box1
    for b2 in boxes2:
        x2, y2, w2, h2 = b2
        x2_min = x2 - w2/2
        x2_max = x2 + w2/2
        y2_min = y2 - h2/2
        y2_max = y2 + h2/2
        dx = min(x1_max, x2_max) - max(x1_min, x2_min)
        dy = min(y1_max, y2_max) - max(y1_min, y2_min)
        if (dx >= 0) and (dy >= 0):
            area_overlap = dx * dy
            area_box1 = (x1_max - x1_min) * (y1_max - y1_min)
            if area_overlap / area_box1 > threshold:
                return True
    return False

with gr.Blocks(theme=gr.themes.Base(primary_hue="teal", secondary_hue="teal", neutral_hue="slate")) as iface:
    gr.Markdown("""<div style="text-align: center;"><h1>NESTLE - STOCK COUNTING</h1></div>""")
    with gr.Row():
        with gr.Column():
            input_image = gr.Image(type="pil", label="Input Image")
        with gr.Column():
            output_image = gr.Image(label="Detect Object")
        with gr.Column():
            output_text = gr.Textbox(label="Counting Object")
    
    # Tombol untuk memproses input
    detect_button = gr.Button("Detect")
    
    # Hubungkan tombol dengan fungsi deteksi
    detect_button.click(
        fn=detect_combined, 
        inputs=input_image, 
        outputs=[output_image, output_text]
    )